© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108205
    Prev
    Next
    INDEX
    Explanations

    code/data strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mts
    -0.28
     inland
    -0.26
    arranty
    -0.25
     Tester
    -0.25
    æIJĶ
    -0.25
    Ĩµ
    -0.25
    æ³ģ
    -0.25
     Crate
    -0.24
    eca
    -0.24
    TestData
    -0.24
    POSITIVE LOGITS
     dis
    0.30
    èģĮ
    0.28
    çī¹åĪ«å£°æĺİ
    0.27
    æĽ²æĬĺ
    0.27
     pu
    0.26
    éĵģ
    0.25
    å°Ĭéĩį
    0.25
    dis
    0.25
    b
    0.25
     und
    0.24
    Activations Density 3.534%

    No Known Activations